skills.rest
Aadi-110i
Aadi-110iCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

prompt-engineering

Applies prompt engineering techniques for LLMs, image generators, and video models via the inference.sh CLI.

Updated Jul 28, 2026
Search Tags:#prompt engineering#image generation#chain-of-thought#few-shot#inference.sh#llm prompting#negative prompts
One-click install
npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill prompt-engineering-aadi-110i
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: prompt-engineering
Source: https://github.com/Aadi-110i/PEP-PROJECT/tree/main/skills/prompt-engineering
Command: npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill prompt-engineering-aadi-110i

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Crafting effective prompts for AI models is inconsistent and often produces unpredictable outputs. This Skill provides structured prompt patterns, templates, and model-specific guidance for LLMs, image generators, and video models, all runnable through the inference.sh CLI. ## Core Features & Use Cases - LLM Prompting Patterns: Covers role prompting, chain-of-thought, few-shot examples, constraint setting, and structured JSON output for models like Claude and GPT-4. - Image & Video Prompting: Provides subject/style/composition structures, negative prompts, camera movement keywords, and temporal keywords for FLUX and Veo models. - Prompt Templates & Iterative Refinement: Includes ready-made templates for code review and content writing, plus a workflow for progressively refining prompts. - Use Case: A developer needs a model to return strict JSON sentiment analysis results. They apply the output format specification pattern with a schema and few-shot examples to get consistent, parseable responses. ## Quick Start Ask the AI to run a well-structured prompt through the belt CLI, such as requesting a chain-of-thought solution or a JSON-formatted sentiment analysis using the openrouter/claude-sonnet-45 app.

Frequently Asked Questions about prompt-engineering

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I write better prompts for LLMs like Claude or GPT-4?▼

Structure prompts as role plus task plus constraints plus output format. Use techniques like chain-of-thought for reasoning, few-shot examples for style consistency, and explicit output format specifications such as JSON schemas for parseable results.

How to use negative prompts in image generation with FLUX?▼

Pass a negative_prompt field alongside the prompt when running falai/flux-dev through the belt CLI. List unwanted elements such as blurry, distorted, watermark, or low quality to steer the model away from common artifacts.

What is chain-of-thought prompting and when should I use it?▼

Chain-of-thought prompting asks the model to reason step by step before giving a final answer. Use it for math problems, logic puzzles, and multi-step analysis where intermediate reasoning improves accuracy.

Does this prompting guide work with video generation models like Veo?▼

Yes, it includes a video prompting section covering shot type, subject, action, setting, and style structure. It documents camera movement keywords and temporal terms like slow motion and timelapse for google/veo-3-1-fast.

Why does my AI model return inconsistent output formats?▼

Inconsistent output usually comes from missing format specifications in the prompt. Fix it by explicitly stating the desired format, providing a JSON schema, and adding few-shot examples showing exact expected outputs.

What are the limitations of prompt engineering for consistent results?▼

Prompt engineering cannot guarantee deterministic outputs since models remain probabilistic. Overly long prompts cause models to lose focus, and conflicting instructions confuse them, so prioritize key information and remove contradictions.

Related Skills

Explore More Content & Communication Skills→
inference-shinference-sh
723

happyhorse

Generate and edit videos with Alibaba HappyHorse 1.0 models via the inference.sh CLI.

Official
Intermediate
tonone-aitonone-ai
69

cortex-prompt

Design and evaluate versioned prompts for LLMs with automated test cases.

Official
Advanced
JStaRFilmsJStaRFilms
23

prompt-engineering

Design effective prompts and system prompts for LLMs, image, and video models.

Community
Intermediate
doanchienthangdevdoanchienthangdev
4

LLMOps

Manages LLM lifecycle including prompts, RAG pipelines, versioning, A/B testing, evaluation, deployment, monitoring, and cost tracking.

Community
Advanced